Bookworm continual learning: beyond zero-shot learning and continual learning [article]

Kai Wang, Luis Herranz, Anjan Dutta, Joost van de Weijer
2020 arXiv   pre-print
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning
more » ... bility, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.
arXiv:2006.15176v3 fatcat:4xpvuzkrwffvzoivry3w7mdtem